---
library_name: transformers
pipeline_tag: text-generation
tags:
- glm4_moe
- GPTQ
- Int4-Int8Mix
- 量化修复
- vLLM
base_model:
- zai-org/GLM-4.5
base_model_relation: quantized
---
# GLM-4.5-GPTQ-Int4-Int8Mix
Base model [zai-org/GLM-4.5](https://huggingface.co/zai-org/GLM-4.5)
### 【VLLM Launch Command for 8-GPU Single Node】
Note: When launching this model on 8 GPUs, you must include --enable-expert-parallel, otherwise expert tensor partitioning will fail due to mismatch. This flag is not required for 4-GPU setups.
```
CONTEXT_LENGTH=32768
vllm serve \
QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix \
--served-model-name GLM-4.5-GPTQ-Int4-Int8Mix \
--enable-expert-parallel \
--swap-space 16 \
--max-num-seqs 512 \
--max-model-len $CONTEXT_LENGTH \
--max-seq-len-to-capture $CONTEXT_LENGTH \
--gpu-memory-utilization 0.9 \
--tensor-parallel-size 8 \
--trust-remote-code \
--disable-log-requests \
--host 0.0.0.0 \
--port 8000
```
### 【Dependencies】
```
vllm==0.10.0
```
### 【Model Update】
```
2025-07-30
1. fast commit
```
### 【Model Files】
| File Size | Last Updated |
|---------|--------------|
| `192GB` | `2025-07-30` |
### 【Model Download】
```python
from huggingface_hub import snapshot_download
snapshot_download('QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")
```
### 【Overview】
# GLM-4.5
👋 Join our Discord community.
📖 Check out the GLM-4.5 technical blog.
📍 Use GLM-4.5 API services on Z.ai API Platform (Global) or
Zhipu AI Open Platform (Mainland China).
👉 One click to GLM-4.5.
## Model Introduction
The **GLM-4.5** series models are foundation models designed for intelligent agents. GLM-4.5 has **355** billion total parameters with **32** billion active parameters, while GLM-4.5-Air adopts a more compact design with **106** billion total parameters and **12** billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.
Both GLM-4.5 and GLM-4.5-Air are hybrid reasoning models that provide two modes: thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses.
We have open-sourced the base models, hybrid reasoning models, and FP8 versions of the hybrid reasoning models for both GLM-4.5 and GLM-4.5-Air. They are released under the MIT open-source license and can be used commercially and for secondary development.
As demonstrated in our comprehensive evaluation across 12 industry-standard benchmarks, GLM-4.5 achieves exceptional performance with a score of **63.2**, in the **3rd** place among all the proprietary and open-source models. Notably, GLM-4.5-Air delivers competitive results at **59.8** while maintaining superior efficiency.
For more eval results, show cases, and technical details, please visit
our [technical blog](https://z.ai/blog/glm-4.5). The technical report will be released soon.
The model code, tool parser and reasoning parser can be found in the implementation of [transformers](https://github.com/huggingface/transformers/tree/main/src/transformers/models/glm4_moe), [vLLM](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/glm4_moe_mtp.py) and [SGLang](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/glm4_moe.py).
## Quick Start
Please refer our [github page](https://github.com/zai-org/GLM-4.5) for more detail.
